基于BP神经网络建立二次润叶工艺参数的预测模型

doi:10.16180/j.cnki.issn1007-7820.2022.09.012

Abstract

Abstract:

In this study, the influence of the process parameter setting of the hot-air leaf moisturizer on the quality index of the exit leaf during the secondary leaf conditioning of threshing and redrying is studied, and the corresponding prediction model is established. A BP neural network prediction model is established based on the characteristics of the secondary leaf conditioning process data. The current popular neural network writing framework TensorFlow's high-level API interface is called to construct the neural network structure. The activation function, optimizer, number of hidden layer neurons and other key parameters are gradually adjusted in the neural network structure to make the prediction result of the test set reach the best state. By inputting the parameters of the front steam nozzle pressure, front-end water flow rate, hot air temperature, return air temperature, feed blade temperature, and feed blade moisture combination, the two key tobacco leaf evaluation indicators, namely, outlet leaf moisture and temperature, are predicted. According to the mean square error, root mean square error, and average absolute error of the prediction results, it is concluded that when the number of neurons in the hidden layer is 7, the activation function selects ReLU, and the optimizer selects RMSprop, the effect is the best.

Key words: BP neural network, secondary leaf conditioning, TensorFlow, activation function, optimizer, exit leaf temperature, exit leaf moisture, mean square error

CLC Number:

TP399

ZHOU Yongchang,HUANG Yayu. Establishment of a Predictive Model of the Process Parameters of Secondary Moisturizing Based on BP Neural Network[J].Electronic Science and Technology, 2022, 35(9): 79-86.

Figures/Tables 12

Table 1.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Table 2.

Figure 7.

Figure 8.

Figure 9.

Table 3.

References 19

[1]	华明德. 对我国打叶复烤工业发展中若干问题的研究[J]. 中国烟草学报, 1998(2):6-13.
	Hua Mingde. Study on the issues relating to the development of leaf tobacco threshing and redrying[J]. Acta Tabacaria Sinica, 1998(2):6-13.
[2]	王跃昆, 华一崑, 李红伟, 等. 打叶复烤研究进展概述[J]. 江西农业学报, 2013, 25(12):57-61.
	Wang Yuekun, Hua Yikun, Li Hongwei, et al. Overview of the research progress of threshing and redrying[J]. Acta Agriculturae Jiangxi, 2013, 25(12):57-61.
[3]	刘政钦. 打叶复烤润叶新工艺加工方式的探究[C]. 南宁: 构建新体系激发新活力-广西烟草学会2019年优秀论文集, 2020.
	Liu Zhengqin. Research on the new processing method of threshing, redrying and moisturizing leaves[C]. Nanning:Constructing a New System Stimulate New Vitality-Outstanding papers of Guangxi Tobacco Society in 2019, 2020.
[4]	龙明海, 张晓龙, 汪显国, 等. 打叶复烤润叶方式对烟叶质量的影响[J]. 湖北农业科学, 2016, 55(1):108-111.
	Long Minghai, Zhang Xiaolong, Wang Xianguo, et al. Effects of moistening method on quality of flue-cured tobacco of threshing and redrying[J]. Hubei Agricultural Sciences, 2016, 55(1):108-111.
[5]	何光瑜. 打叶复烤热风润叶机自抗扰控制算法研究[D]. 长沙: 湖南大学, 2018.
	He Guangyu. Research on auto-disturbance rejection control algorithm for tobacco leaf moisture of hot-winding conditioning cylinder in threshing and redrying[D]. Changsha: Hunan University, 2018.
[6]	连长伟, 张腾健, 卢敏瑞, 等. 不同润叶强度对打叶复烤在制品质量及能源消耗的影响[J]. 安徽农业科学, 2020, 48(15):194-196.
	Lian Changwei, Zhang Tengjian, Lu Minrui, et al. Effects of different moistening strength on the quality and energy consumption of products in the threshing and redrying process[J]. Journal of Anhui Agricultural Sciences, 2020, 48(15):194-196.
[7]	王发勇, 牛绍辉, 徐超, 等. 基于烟片结构和保香加工的润叶参数模式筛选[J]. 江苏农业科学, 2020, 48(9):223-227.
	Wang Fayong, Niu Shaohui, Xu Chao, et al. Selection of leaf moistening parameter model based on tobacco leaf structure and fragrance preserving processing[J]. Jiangsu Agricultural Sciences, 2020, 48(9):223-227.
[8]	陈成, 周明, 杨兴成, 等. 改进润叶机进料方式的探讨[J]. 现代农机, 2019(6):45-46.
	Chen Cheng, Zhou Ming, Yang Xingcheng, et al. Discussion on improving the feeding mode of leaf conditioner[J]. Modern Agricultural Machinery, 2019(6): 45-46.
[9]	王朝明. 新型热风润叶循环系统的设计及应用[J]. 设备监理, 2019(5):48-50.
	Wang Chaoming. The design and application of a new type of hot air moisturizing leaf circulation system[J]. Plant Engineering Consultants, 2019(5):48-50.
[10]	刘彦岭, 王泽理, 周强, 等. 打叶复烤润叶段水分温度控制模型的建立[J]. 安徽农学通报, 2017, 23(22):109-111.
	Liu Yanling, Wang Zeli, Zhou Qiang, et al. Establishment of control model of threshing and redrying condition leaf section with tobacco water and temperature[J]. Anhui Agricultural Science Bulletin, 2017, 23(22):109-111.
[11]	段雨佳, 鞠婷. 基于深度学习的代码审查意见有效性评估[J]. 电子科技, 2020, 33(1):39-45.
	Duan Yujia, Ju Ting. Evaluation of code review comments based on deep learning[J]. Electronic Science and Technology, 2020, 33(1):39-45.
[12]	程俊华, 曾国辉, 刘瑾. 基于深度学习的复杂背景图像分类方法研究[J]. 电子科技, 2020, 33(12):59-66.
	Cheng Junhua, Zeng Guohui, Liu Jin. Research on complex background image classification method based on deep learning[J]. Electronic Science and Technology, 2020, 33(12):59-66.
[13]	闫超, 孙占全, 田恩刚, 等. 基于深度学习的医学图像分割技术研究进展[J]. 电子科技, 2021, 34(2):7-11.
	Yan Chao, Sun Zhanquan, Tian Engang, et al. Research progress of medical image segmentation based on deep learning[J]. Electronic Science and Technology, 2021, 34(2):7-11.
[14]	唐云岚. 集成神经网络和多目标进化算法的卷烟产品参数优化设计方法及应用研究[D]. 长沙: 国防科学技术大学, 2008.
	Tang Yunlan. An Integrated design approach based on neural network and multi-objective evolutionary algorithm in cigarette product parameter optimization and its application[D]. Changsha: National University of Defense Technology, 2008.
[15]	蔡兵. BP神经网络隐层结构的设计方法[J]. 通化师范学院学报, 2007, 28(2):18-19.
	Cai Bing. Design method on structure of implicit strata in BP neural network[J]. Journal of Tonghua Teachers University, 2007, 28(2):18-19.
[16]	范佳妮, 王振雷, 钱锋. BP人工神经网络隐层结构设计的研究进展[J]. 控制工程, 2005(S1):109-113.
	Fan Jiani, Wang Zhenlei, Qian Feng. Research pogress structure design of hidden layer in BP artificial neural network[J]. Control Engineering of China, 2005(S1):109-113.
[17]	Zou F, Shen L, Jie Z, et al. A Sufficient condition for convergences of adam and rmsprop[C]. Seoul: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.
[18]	Xu D, Zhang S, Zhang H, et al. Convergence of the RMSProp deep learning method with penalty for nonconvex optimization[J]. Neural Networks, 2021, 13(9):17-23. doi: 10.1016/S0893-6080(99)00097-0
[19]	李跃锋, 姜焕元, 刘志平, 等. 烟叶温度和含水率与打叶质量的关系[J]. 烟草科技, 2005(2):5-6.
	Li Yuefeng, Jiang Huanyuan, Liu Zhiping, et al. Relationship of threshing quality with temperature and moisture content of tobacco leaf[J]. Tobacco Science & Technology, 2005(2):5-6.

编号	前蒸汽喷嘴压力 /Bar	前端加水流量 /L·h^-1	热风温度 /℃	回风温度 /℃	进料叶片温度 /℃	进料叶片水分 /%	出口叶片温度 /℃	出口叶片水分 /%
1	0.00	250.00	80.00	50.00	29.30	14.47	45.33	22.80
2	0.10	250.00	94.00	60.00	29.60	13.36	53.00	18.63
3	0.20	170.00	106.00	67.00	29.70	13.81	60.00	17.15
4	0.35	220.00	118.00	78.00	28.90	14.32	61.00	20.28
5	0.46	190.00	135.00	82.00	29.70	14.32	70.33	18.01
6	0.00	200.00	80.00	50.00	29.90	14.57	41.67	22.40
7	0.10	200.00	92.00	57.00	29.20	15.12	50.00	20.06
8	0.20	250.00	106.00	67.00	28.60	14.81	58.67	21.86
9	0.33	210.00	117.00	73.00	29.40	19.50	62.33	21.25
10	0.46	195.00	132.00	80.00	29.50	15.31	68.33	19.90

隐藏层神经元数目	MSE	RMSE	MAE
5	15.54	3.94	2.82
6	9.65	3.11	2.09
7	7.17	2.68	1.83
8	14.15	3.76	2.76
9	11.49	3.39	2.51
10	9.99	3.16	2.40
11	12.76	3.57	2.68

优化器	MSE	RMSE	MAE
RMSprop	7.17	2.68	1.83
SGD	17.83	4.22	2.81
Adagrad	38.44	6.20	4.68
Adam	12.70	3.56	2.36

Establishment of a Predictive Model of the Process Parameters of Secondary Moisturizing Based on BP Neural Network

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 19

Related Articles 15

Metrics

Comments

Recommended 10

[1]	ZHANG Chongchong,HUANG Yayu. A GA-BP Neural Network for Predicting the Structure of Leaf Tobacco [J]. Electronic Science and Technology, 2022, 35(6): 35-42.
[2]	ZHAO Doudou,ZHANG Wei. Soft-Sensing of Effluent BOD Based on VW-IGRBF Neural Network [J]. Electronic Science and Technology, 2022, 35(5): 26-32.
[3]	Li HUA,Jian YANG,Tianchen YUAN,Ruigang SONG. Track Disease Diagnosis Method Based on VMD and BP Neural Network [J]. Electronic Science and Technology, 2022, 35(4): 40-46.
[4]	CHU Ping,NI Wei. Design of FPGA-Based SqueezeNet Inference Accelerator [J]. Electronic Science and Technology, 2022, 35(2): 20-26.
[5]	MENG Xiaojiao,ZHANG Shiwei,LI Xiaojian,LI Minyue,SONG Bingxin,LU Hongmin. An Evaluation Method of Vehicle-Mounted Communication Equipment Performance Based on BP Neural Network [J]. Electronic Science and Technology, 2021, 34(5): 24-28.
[6]	ZHU Yifeng. Indoor Positioning Algorithm Based on WiFi-BP [J]. Electronic Science and Technology, 2020, 33(8): 74-79.
[7]	SUN Mingyang,XIE Zidian,HAN Long,BI Sida. Motor Vibration Signal Denoising of Adaptive Threshold Function Wavelet Algorithm [J]. Electronic Science and Technology, 2020, 33(1): 63-67.
[8]	ZHANG Changqing,YANG Nan. License Plate Character Recognition Technology Based on Hybrid Neural Network [J]. Electronic Science and Technology, 2019, 32(9): 51-54.
[9]	PAN Shui. Research on Minimum Mean Square Error Fitting Height Estimation Algorithm for Radar Altimeter [J]. Electronic Science and Technology, 2019, 32(8): 22-26.
[10]	GUAN Sheng,RUAN Fangming,ZHOU Kui,SU Ming,WANG Heng,DENG Di,LI Jia. Analysis of Discharge Parameters Affected by BP Neural Network Predicting Electrode Velocity [J]. Electronic Science and Technology, 2019, 32(6): 43-48.
[11]	WANG Hongchuang,HU Xiaohui,LI Wei. An Image Denoising Algorithm Based on Improved Threshold Function Contourlet Domain [J]. Electronic Science and Technology, 2019, 32(4): 44-48.
[12]	YANG Jiayi. Research on a Technology of Missile Fault Automatic Diagnosis Based on BP Neural Network [J]. , 2018, 31(4): 48-.
[13]	WEI Shuang. Research on Mouth Type Classification Algorithm Based on BP Neural Network [J]. , 2016, 29(8): 89-.
[14]	JIN Yanfei, ZHANG Huilin, ZHANG Song, SHI Chaoran, LI Rongwei. Comparison of MPPT Control Methods Based on GABPNN and Perturb & Observe Algorithm [J]. , 2016, 29(8): 145-.
[15]	DENG Yumei. An Approach to Threat Assessment of Aerial Targets Based on BP Neural Network Algorithm Using Ant Colony Optimization [J]. , 2016, 29(7): 33-.